Boring Log Extractor (PDF → DIGGS)

Reads a scanned or born-digital boring log PDF — header, depths, blow counts, soil descriptions, groundwater — and returns structured DIGGS XML you can load into any DIGGS-aware tool. The same pipeline that digitized hundreds of thousands of public logs on Geosetta.

Open the extractor app →

How it works

• A vision-language model reads each page as an image and a document, so it copes with photocopies, handwriting and unusual forms as well as gINT-style sheets.
• The page is first classified (boring log, CPT sounding, lab sheet, cover page) so only log pages are extracted.
• Output is DIGGS 3.0 XML; you can validate it with the DIGGS Validator and open it in the DIGGS Viewer.

What to expect

• Blow counts, depths, sample types and descriptions come through reliably; check elevations and coordinates, which are the fields logs most often omit or state ambiguously.
• Processing is queued; large reports take a few minutes. API access uses per-key credits.

Not sure what a boring log looks like?

• See the annotated example boring logs on this site — real PDFs from state DOTs, with a guide to each column.

Other DIGGS tools

DIGGS ValidatorAGS ↔ DIGGS ConverterDIGGS Viewer Example boring logs

DIGGS is the Data Interchange for Geotechnical and Geoenvironmental Specialists, an open XML standard maintained by the DIGGS community and ASCE Geo-Institute. Geosetta is a nonprofit and provides these tools free of charge; see the terms and disclaimer.